© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 205454
    Prev
    Next
    INDEX
    Explanations

    Chrome, Firefox, Browser options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_20_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     બના
    0.50
     verduras
    0.47
    통산
    0.45
     unaffected
    0.45
     рука
    0.43
     Ova
    0.43
     Btu
    0.43
    叄
    0.43
     Tenggara
    0.42
     इच्छुक
    0.42
    POSITIVE LOGITS
     y
    0.57
    ly
    0.44
    ization
    0.44
    covery
    0.43
    nej
    0.43
    ipping
    0.43
     me
    0.41
     tôi
    0.40
    "
    0.39
    ith
    0.39
    Activations Density 0.000%

    No Known Activations